Ultromics has developed the world’s most accurate echocardiography AI diagnostics software to boost the detection of coronary heart disease to over 90 percent.
Building on the foundation of almost a decade of imaging research by its team at Oxford University, Ultromics is releasing a new approach to the world of cardiovascular diagnostics that leverages the power of machine learning.
The system is predicted to save the UK’s National Health Service (NHS) billions of pounds by enabling heart disease and lung cancer cases to be diagnosed earlier and more accurately, avoiding expensive treatment when it’s not needed and providing it as soon as possible, when it is.
Ultromics will become available to NHS hospitals for free this summer. Sir John Bell, Chairman of the Office for Strategic Coordination of Health Research (OSCHR), told BBC news:
“There is about £2.2bn spent on pathology services in the NHS. You may be able to reduce that by 50 percent. AI may be the thing that saves the NHS,” Bell said.
Read more: Apple Watch KardiaBand accessory shows it’s time for IoT in healthcare
The brains behind Ultromics AI diagnostics
We’ve previously reported on the potential of AI in diagnostics. AI is able to detect things in x-rays and ultrasounds that doctors simply can’t.
The technology extracts more than 80,000 data points from a single echocardiogram image and uses machine learning to analyse them, overcoming subjectivity and increasing diagnostic accuracy of coronary heart disease from 80 percent to over 90 percent. This is thanks to the AI being trained with one of the world’s largest imaging databases.
Clinical trials across six cardiology units have proved the system’s diagnostics capabilities. Professor Paul Leeson, a cardiologist who helped develop Ultromics, says that the results show that the system has greatly outperformed his fellow heart specialists.
“As cardiologists, we accept that we don’t always get it right at the moment. But now there is a possibility that we may be able to do better.”
Of the 60,000 heart scans carried out each year around 12,000 are misdiagnosed, costing the NHS £600 million in needless surgery and the treatment of patients who had heart attacks after being given the all-clear.
Ultromics is well aware of the potential of AI to transform ultrasound interpretation more widely. The company is continuing work on a product pipeline that is built on one of the world’s largest research databases of echo images. These are transformative times for diagnostic science and AI has a bright future in healthcare.
Plus, with budgetary restrictions straining the NHS to its limits, anything that can ease the pressure will be eagerly welcomed by hospitals across the country.
Read more: GDPR could have connected healthcare providers feeling queasy in 2018